Classifying Signals on Irregular Domains via Convolutional Cluster Pooling

Angelo Porrello, Davide Abati, Simone Calderara, Rita Cucchiara
Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics, PMLR 89:1388-1397, 2019.

Abstract

We present a novel and hierarchical approach for supervised classification of signals spanning over a fixed graph, reflecting shared properties of the dataset. To this end, we introduce a Convolutional Cluster Pooling layer exploiting a multi-scale clustering in order to highlight, at different resolutions, locally connected regions on the input graph. Our proposal generalises well-established neural models such as Convolutional Neural Networks (CNNs) on irregular and complex domains, by means of the exploitation of the weight sharing property in a graph-oriented architecture. In this work, such property is based on the centrality of each vertex within its soft-assigned cluster. Extensive experiments on NTU RGB+D, CIFAR-10 and 20NEWS demonstrate the effectiveness of the proposed technique in capturing both local and global patterns in graph-structured data out of different domains.

Cite this Paper


BibTeX
@InProceedings{pmlr-v89-porrello19a, title = {Classifying Signals on Irregular Domains via Convolutional Cluster Pooling}, author = {Porrello, Angelo and Abati, Davide and Calderara, Simone and Cucchiara, Rita}, booktitle = {Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics}, pages = {1388--1397}, year = {2019}, editor = {Chaudhuri, Kamalika and Sugiyama, Masashi}, volume = {89}, series = {Proceedings of Machine Learning Research}, month = {16--18 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v89/porrello19a/porrello19a.pdf}, url = {http://proceedings.mlr.press/v89/porrello19a.html}, abstract = {We present a novel and hierarchical approach for supervised classification of signals spanning over a fixed graph, reflecting shared properties of the dataset. To this end, we introduce a Convolutional Cluster Pooling layer exploiting a multi-scale clustering in order to highlight, at different resolutions, locally connected regions on the input graph. Our proposal generalises well-established neural models such as Convolutional Neural Networks (CNNs) on irregular and complex domains, by means of the exploitation of the weight sharing property in a graph-oriented architecture. In this work, such property is based on the centrality of each vertex within its soft-assigned cluster. Extensive experiments on NTU RGB+D, CIFAR-10 and 20NEWS demonstrate the effectiveness of the proposed technique in capturing both local and global patterns in graph-structured data out of different domains.} }
Endnote
%0 Conference Paper %T Classifying Signals on Irregular Domains via Convolutional Cluster Pooling %A Angelo Porrello %A Davide Abati %A Simone Calderara %A Rita Cucchiara %B Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2019 %E Kamalika Chaudhuri %E Masashi Sugiyama %F pmlr-v89-porrello19a %I PMLR %P 1388--1397 %U http://proceedings.mlr.press/v89/porrello19a.html %V 89 %X We present a novel and hierarchical approach for supervised classification of signals spanning over a fixed graph, reflecting shared properties of the dataset. To this end, we introduce a Convolutional Cluster Pooling layer exploiting a multi-scale clustering in order to highlight, at different resolutions, locally connected regions on the input graph. Our proposal generalises well-established neural models such as Convolutional Neural Networks (CNNs) on irregular and complex domains, by means of the exploitation of the weight sharing property in a graph-oriented architecture. In this work, such property is based on the centrality of each vertex within its soft-assigned cluster. Extensive experiments on NTU RGB+D, CIFAR-10 and 20NEWS demonstrate the effectiveness of the proposed technique in capturing both local and global patterns in graph-structured data out of different domains.
APA
Porrello, A., Abati, D., Calderara, S. & Cucchiara, R.. (2019). Classifying Signals on Irregular Domains via Convolutional Cluster Pooling. Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 89:1388-1397 Available from http://proceedings.mlr.press/v89/porrello19a.html.

Related Material